Y. Woldeyohannes, Ali Mohammadkhan, K. Ramakrishnan, Yuming Jiang
{"title":"A scalable resource allocation scheme for NFV: Balancing utilization and path stretch","authors":"Y. Woldeyohannes, Ali Mohammadkhan, K. Ramakrishnan, Yuming Jiang","doi":"10.1109/ICIN.2018.8401631","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401631","url":null,"abstract":"Network Function Virtualization (NFV) implements network middlebox functions in software, enabling them to be more flexible and dynamic. NFV resource allocation methods can exploit the capabilities of virtual- ization to dynamically instantiate network functions (NFs) to adapt to network conditions and demand. Deploying NFs requires decisions for both NF placement and routing of flows through these NFs in accordance with the required sequence of NFs that process each flow. The challenge in developing NFV resource allocation schemes is the need to manage the dependency between flow-level (routing) and network-level (placement) decisions. We model the NFV resource allocation problem as a multi-objective mixed integer linear programming problem, solving both flow-level and network-level decisions simultaneously. The optimal solution is capable of providing placement and routing decisions at a small scale. Based on the learnings from the optimal solution, we develop ClusPR, a heuristic solution that can scale to larger, more practical network environments supporting a larger number of flows. By elegantly capturing the dependency between flow routing and NF placement, ClusPR strikes a balance between minimizing path stretch and maximizing network utilization. Our experiments show ClusPR is capable of achieving near-optimal solution for a large sized network, in an acceptable time. Compared to state-of-the- art approaches, ClusPR is able to decrease the average normalized delay by a factor of 1.2–1.6× and the worst- case delay by 9–10×, with the same or slightly better network utilization.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116203061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. V. Do, Nam H. Do, Isvan Kispal, Nándor Galambosi, C. Rotter, L. Nemeth
{"title":"A big switch abstraction to support service function chaining in cloud infrastructure","authors":"T. V. Do, Nam H. Do, Isvan Kispal, Nándor Galambosi, C. Rotter, L. Nemeth","doi":"10.1109/ICIN.2018.8401620","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401620","url":null,"abstract":"The concept of Service Function Chaining and Network Functions Virtualisation provides a great degree of flexibility for the rapid deployment of new services in service providers' environments. Data model, metadata and descriptors for virtual network function elements, virtual links, connection points, Virtual Network Function Forwarding Graphs and Network Forwarding paths are specified. In this paper, we present a big switch abstraction to realize Virtual Network Function Forwarding Graphs and network forwarding paths. We show that a configuration that takes into account the bidirectional nature of Linux bridges and the open virtual switch can result in a good bandwidth for network forwarding paths.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121637628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A DNS-based information-centric network architecture open to multiple protocols for transfer of data objects","authors":"A. Eriksson, A. Malik","doi":"10.1109/ICIN.2018.8401595","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401595","url":null,"abstract":"In this paper, we present the information-centric NEO (Networked Object) architecture. To enable reuse of existing network protocols and naming formats, NEO uses DNS domain names as data object names, as well as DNS proxies and servers that are enhanced for information-centric operation. A key feature of NEO is its openness to a variety of legacy protocols for transfer of data objects, such as HTTP, CoAP or IP multicast. NEO allows for selection of transfer protocol per data object, so that the most optimal protocol can be selected for the data object and use case at hand. Also, NEO can employ clean slate protocols such as CCN or NDN for transfer of data objects. We validate the NEO architecture in a testbed using DNS for resolution of data object names and HTTP, CoAP, IP multicast, and CCN for object transfer. We also describe several features implemented in the NEO testbed, such as policy routing, publisher mobility, publish-subscribe and service chaining for IoT use cases.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134487916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Information retention for disaster-affected networks using content-centric networking","authors":"A. Malik, E. Andersson, B. Ohlman","doi":"10.1109/ICIN.2018.8401588","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401588","url":null,"abstract":"Maintaining communication and information sharing in a disaster situation is a challenging task. A typical consequence of a natural disaster is that communication networks get fragmented. Consequently, information published in one fragment is no longer reachable by users in the other fragments. A number of approaches have been proposed to facilitate information retention in the network, most of them reactive, e.g. using data mules. In this paper we propose proactive measures to share information within the network before it becomes fragmented using Information-Centric Networking (ICN). We have developed a system, using the Content-Centric Networking (CCN) protocol, which proactively replicates content across different parts of the network by taking into account how the network will potentially fragment in the future. We demonstrate the content replication aspect of this system using 16 virtual CCN nodes distributed over 5 potential fragments called “Communities”.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131359123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. L. Pallec, L. Noirie, P. Peloso, Dinh Thai Bui, N. L. Sauze
{"title":"Digital assistance for the automated discovery and deployment of IoT services","authors":"M. L. Pallec, L. Noirie, P. Peloso, Dinh Thai Bui, N. L. Sauze","doi":"10.1109/ICIN.2018.8401599","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401599","url":null,"abstract":"At the dawn of a fully connected world with many different devices, benefiting from the whole richness of IoT services still represents a complex task for end-users. To lessen such a burden, we propose and demonstrate a solution that combines an SDN-based IoT-network platform and a service recommendation assistant. This association allows the discovery and the deployment of IoT services involving multiple connected objects spanning different people and smart environments in a friendly, trustworthy and secured way.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116489665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Traffic modeling for aggregated periodic IoT data","authors":"T. Hossfeld, Florian Metzger, P. Heegaard","doi":"10.1109/ICIN.2018.8401624","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401624","url":null,"abstract":"The Internet of Things (IoT) is emerging in the telecommunication sector, and will bring a very large number of devices that connect to the Internet in the near future. The expected growth in such IoT nodes necessitates appropriate traffic models in order to evaluate their impact on different aspects of networking, e.g., on signaling load in the networks, or on processing load of the data in a cloud. In this paper we analyze the characteristics of aggregated periodic IoT data based on related work, and compare them with a Poisson process as approximation for the superposed traffic as assumed in standardization. Such an approximation is crucial in order to investigate the scalability of an IoT network, as it may be impossible in practice to measure or to simulate large-scale IoT deployments. The accuracy and applicability of the Poisson process is investigated for the use case “IoT cloud”. The results show that the Poisson process may induce large errors depending on the performance metric of interest. This error must be considered by standardization and requires more sophisticated traffic models. As key contributions, we provide realistic traffic models for periodic IoT data, introduce performance metrics for quantifying the bias, and derive reference values as to when the Poisson process can be assumed for aggregated periodic IoT data.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115027558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An experimental evaluation of MPTCP-tunnel-based hybrid access","authors":"Arthur Holzner, R. Winter","doi":"10.1109/ICIN.2018.8401635","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401635","url":null,"abstract":"In numerous countries, the nation-wide roll-out of high-speed Internet access is progressing slowly, in particular in rural areas, where the investment of laying fiber is high compared to potential revenue. Regulatory pressure however has forced ISPs to act and to provide reliable broadband services to all. The solution that has been deployed or is currently being trialed in various countries is to bond existing DSL with existing high-speed wireless data access provided by LTE to deliver an adequate aggregate bandwidth. There are currently at least two technologies being used, based on either layer-3 tunnels (implemented using GRE) or multi-path TCP (MPTCP) proxies that translate regular TCP into a multi-path TCP connection for the access segment of an end-to-end path. In both cases, the respective protocols cannot be used simply as is as either protocol extensions are needed or some sort of elaborate logic needs to be implemented to deal with issues such as packet reordering. Alternatively, it would be possible to simply use MPTCP unmodified as an underlying transport protocol for existing tunneling technologies such as SSH or OpenVPN. Such an approach could be used today without any modifications to software or protocols. While layer-7 tunneling over an MPTCP transport comes with its own merits it has potential drawbacks, such as bad interactions of congestion control feedback loops. In this paper, we experimentally demonstrate the properties of such an approach and contrast the properties of all three approaches as technologies to provide high-speed, reliable broadband to end consumers.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121826284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A systematic fault-tolerant computational model for both crash failures and silent data corruption","authors":"Xiaolong Cui, Zaeem Hussain, T. Znati, R. Melhem","doi":"10.1109/ICIN.2018.8401596","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401596","url":null,"abstract":"As the boundaries between Cloud and HPC continue to blur, it is clear that there is an urgent demand for a systematic computational model that adapts to the computing platform and accommodates the underlying workloads. As computing systems continue to scale out to satisfy the increasingly large demands on computing capacity, power awareness and fault tolerance have become major concerns. This paper proposes a novel computational model that applies to both compute- and data-intensive workloads, and deals with diverse types of faults. Evaluation results demonstrate that the proposed model is able to achieve significant energy savings compared to existing fault tolerance techniques, while maintaining the same level of fault tolerance.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124831403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Destination-specific maximally redundant trees: Design, performance comparison, and applications","authors":"Wolfgang Braun, Daniel Merling, M. Menth","doi":"10.1109/ICIN.2018.8401580","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401580","url":null,"abstract":"Resilient networks react to a failure by reconfiguring routing tables in a network-wide manner and utilizing fast reroute (FRR) in the meanwhile. FRR uses pre-computed backup paths to avoid the failure locally. The existing FRR approaches for IP networks and Software-Defined Networking (SDN) differ in regard to computational complexity, backup path length, additional forwarding state and required capacities. Maximally Redundant Trees (MRTs) are standardized by the IETF and are already available for IP and MPLS networks. In this paper, we propose destination-specific MRTs (dMRTs), an improved variant of MRTs, for protection of IP networks. This mechanism reduces the generated path lengths but increases the computational complexity of the MRT algorithm. We analyze and compare our proposal with simple MRTs and MPLS FRR. We show on a large and publicly available network data base that dMRTs provide significant shorter backup paths compared to simple MRTs and require less forwarding state and network capacities than MPLS FRR. Adapting an existing FRR mechanism for IP networks to SDN enables its deployment in hybrid-SDN networks. Thus, we outline implementation options of dMRTs in IP and MPLS networks and (d)MRTs in SDN. Finally, we discuss the computational overhead of our proposal in the context of (decentralized) IP networks and (centralized) SDNs.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115926712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuansong Qiao, Robert Nolani, Saul Gill, Guiming Fang, Brian A. Lee
{"title":"ThingNet: A micro-service based IoT macro-programming platform over edges and cloud","authors":"Yuansong Qiao, Robert Nolani, Saul Gill, Guiming Fang, Brian A. Lee","doi":"10.1109/ICIN.2018.8401626","DOIUrl":"https://doi.org/10.1109/ICIN.2018.8401626","url":null,"abstract":"The enormous number of things connected to the Internet requires a flexible macro-programming platform to efficiently organize functions and process data. Fog or Edge computing is an emerging architecture to fill the gaps between things and cloud through providing computing, storage and forwarding services close to the end devices. This paper presents ThingNet — a micro-service based macro-programming platform to enable distributed data routing and processing across IoT devices, edges and central cloud. Application providers can deploy, modify, migrate and scale application logic over underlying infrastructures. An application level service function chaining is designed to enable data flow programming. The service functions can be shared by multiple data flows to reduce resource utilisation. The platform is implemented based on open source platforms including Kubernetes and MiNifi. ThingNet has been verified through a proof of concept testbed including Raspberry Pis, Intel NUCs, and Openstack VMs.","PeriodicalId":103076,"journal":{"name":"2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116019104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}